Interactive listening evidence · Base & Medium

Vocal burst 38: Exhausted Groan

Gemini event spans versus independently predicted Base and Medium spans. Hear the clip and inspect both models’ event labels, 20 ms curves and 192 scores.

← All 50 examples ← Previous Next →

38. Exhausted Groan

emolia_c0801VWARM__extremely_low__en.c036.k1

vc_sidon · en/synth · 2.78 s · validation split

3 Gemini eventsBase count 2.6Medium count 2.2

Source key: emolia_c0801__V__WARM__extremely_low__en.c036.k1 · Audio SHA256: dd05fca60b93690af241a0a3f67e93e01a97ea104599a462a0b98408f880b65c

Gemini annotation · selection aid

0.05–0.38 s: Exhausted Groan · group sigh_neg
0.88–1.28 s: Exhausted Groan · group sigh_neg
1.94–2.38 s: Exhausted Groan · group sigh_neg

Base predictions

20 ms frame probability; dashed line = 0.5 threshold

0.04–0.58 s: Throat Clearing 57%, Effort Grunt 11%, Growl 6% · onset 0.99
0.10–0.62 s: Throat Clearing 49%, Effort Grunt 12%, Growl 6% · onset 0.71
0.38–0.98 s: Other / rare burst 17%, Effort Grunt 16%, Throat Clearing 13% · onset 0.53
0.44–0.96 s: Other / rare burst 17%, Effort Grunt 16%, Throat Clearing 12% · onset 0.57
0.58–1.04 s: Other / rare burst 17%, Effort Grunt 16%, Displeased Grunt 10% · onset 0.72
0.66–1.10 s: Effort Grunt 19%, Other / rare burst 16%, Displeased Grunt 12% · onset 0.77
0.72–1.16 s: Effort Grunt 22%, Other / rare burst 16%, Displeased Grunt 12% · onset 0.80
0.80–1.30 s: Effort Grunt 23%, Exhausted Groan 18%, Other / rare burst 15% · onset 0.81
0.86–1.32 s: Effort Grunt 26%, Exhausted Groan 18%, Other / rare burst 14% · onset 0.80
0.94–1.34 s: Effort Grunt 31%, Exhausted Groan 16%, Frustrated Groan 12% · onset 0.80
1.04–1.48 s: Effort Grunt 29%, Exhausted Groan 20%, Other / rare burst 14% · onset 0.85
1.24–1.92 s: Other / rare burst 27%, Effort Grunt 22%, Exhausted Groan 16% · onset 0.72
1.30–2.04 s: Other / rare burst 28%, Effort Grunt 22%, Exhausted Groan 12% · onset 0.61
1.36–1.96 s: Other / rare burst 28%, Effort Grunt 22%, Exhausted Groan 11% · onset 0.56
1.48–1.96 s: Other / rare burst 27%, Effort Grunt 21%, Exhausted Groan 12% · onset 0.85
1.54–1.96 s: Other / rare burst 26%, Effort Grunt 21%, Exhausted Groan 12% · onset 0.53
1.62–2.12 s: Other / rare burst 23%, Effort Grunt 21%, Displeased Grunt 12% · onset 0.70
1.74–2.18 s: Effort Grunt 24%, Other / rare burst 17%, Displeased Grunt 17% · onset 0.85
1.86–2.30 s: Effort Grunt 32%, Displeased Grunt 18%, Other / rare burst 11% · onset 0.77
1.98–2.40 s: Effort Grunt 41%, Displeased Grunt 15%, Exhausted Groan 8% · onset 0.89
2.06–2.46 s: Effort Grunt 42%, Displeased Grunt 12%, Exhausted Groan 12% · onset 0.70
2.18–2.50 s: Effort Grunt 46%, Exhausted Groan 15%, Frustrated Groan 9% · onset 0.87
2.24–2.64 s: Effort Grunt 34%, Exhausted Groan 21%, Frustrated Groan 10% · onset 0.60

Frame-positive regions: 1 · CPS 1.39 · Orange timbre cosine 0.702 · identity cosine 0.717

Medium predictions

20 ms frame probability; dashed line = 0.5 threshold

0.00–0.68 s: Throat Clearing 61%, Effort Grunt 17%, Other / rare burst 5% · onset 0.98
0.08–0.68 s: Throat Clearing 54%, Effort Grunt 19%, Other / rare burst 5% · onset 0.66
0.44–1.32 s: Effort Grunt 30%, Exhausted Groan 20%, Other / rare burst 10% · onset 0.74
0.54–1.34 s: Effort Grunt 29%, Exhausted Groan 23%, Other / rare burst 10% · onset 0.75
0.60–1.34 s: Effort Grunt 29%, Exhausted Groan 22%, Other / rare burst 10% · onset 0.74
0.68–1.48 s: Effort Grunt 32%, Exhausted Groan 20%, Other / rare burst 13% · onset 0.67
0.84–1.58 s: Effort Grunt 34%, Exhausted Groan 19%, Other / rare burst 14% · onset 0.71
0.92–1.54 s: Effort Grunt 34%, Exhausted Groan 17%, Other / rare burst 14% · onset 0.78
1.00–1.76 s: Effort Grunt 31%, Exhausted Groan 23%, Other / rare burst 15% · onset 0.74
1.10–1.76 s: Effort Grunt 29%, Exhausted Groan 24%, Other / rare burst 17% · onset 0.50
1.34–2.08 s: Other / rare burst 25%, Effort Grunt 23%, Exhausted Groan 17% · onset 0.66
1.44–2.08 s: Effort Grunt 22%, Other / rare burst 22%, Exhausted Groan 19% · onset 0.73
1.50–2.14 s: Effort Grunt 23%, Other / rare burst 22%, Exhausted Groan 18% · onset 0.82
1.60–2.24 s: Effort Grunt 29%, Other / rare burst 21%, Exhausted Groan 17% · onset 0.81
1.72–2.32 s: Effort Grunt 37%, Exhausted Groan 18%, Other / rare burst 15% · onset 0.77
1.88–2.50 s: Effort Grunt 37%, Exhausted Groan 23%, Other / rare burst 12% · onset 0.75
1.98–2.54 s: Effort Grunt 39%, Exhausted Groan 20%, Other / rare burst 11% · onset 0.86
2.12–2.64 s: Effort Grunt 36%, Exhausted Groan 22%, Frustrated Groan 10% · onset 0.77
2.20–2.78 s: Exhausted Groan 31%, Effort Grunt 29%, Frustrated Groan 8% · onset 0.71

Frame-positive regions: 1 · CPS 0.55 · Orange timbre cosine 0.714 · identity cosine 0.680

All 192 scalar scores: Base and Medium raw plus reference z

Target	Base raw	Base z	Medium raw	Medium z
`emo_Affection`	0.03	0.05	0.05	0.07
`emo_Amusement`	0.06	0.07	0.10	0.12
`emo_Anger`	0.16	0.26	0.16	0.26
`emo_Astonishment_Surprise`	0.03	0.04	0.04	0.05
`emo_Awe`	0.03	0.06	-0.05	-0.11
`emo_Bitterness`	0.03	0.04	0.11	0.23
`emo_Concentration`	0.67	0.04	0.90	0.35
`emo_Confusion`	-0.01	-0.02	-0.01	-0.02
`emo_Contemplation`	0.63	0.91	0.42	0.56
`emo_Contempt`	0.00	0.01	0.05	0.12
`emo_Contentment`	0.18	0.35	0.23	0.45
`emo_Disappointment`	0.29	0.41	0.36	0.51
`emo_Disgust`	0.11	0.21	0.03	0.06
`emo_Distress`	1.42	1.72	1.14	1.39
`emo_Doubt`	0.12	0.24	0.05	0.09
`emo_Elation`	-0.01	-0.02	-0.00	-0.02
`emo_Embarrassment`	0.03	-0.04	0.04	-0.00
`emo_Emotional_Numbness`	0.29	0.31	0.39	0.42
`emo_Fatigue_Exhaustion`	3.07	5.65	2.90	5.34
`emo_Fear`	0.18	0.27	0.07	0.09
`emo_Helplessness`	1.16	1.67	1.24	1.79
`emo_Hope_Enthusiasm_Optimism`	0.15	0.04	0.12	0.01
`emo_Impatience_and_Irritability`	0.43	0.39	0.52	0.52
`emo_Infatuation`	0.00	0.03	0.04	0.10
`emo_Interest`	0.49	-1.22	0.33	-1.39
`emo_Intoxication_Altered_States_of_Consciousness`	0.07	0.17	0.07	0.18
`emo_Jealousy_and_Envy`	-0.07	-0.28	0.01	-0.12
`emo_Longing`	-0.04	-0.20	0.09	0.01
`emo_Malevolence_Malice`	0.05	-0.01	0.05	-0.01
`emo_Pain`	1.08	1.87	1.25	2.15
`emo_Pleasure_Ecstasy`	0.07	0.08	0.12	0.17
`emo_Pride`	0.00	0.00	-0.00	-0.00
`emo_Relief`	0.21	0.26	0.30	0.39
`emo_Sadness`	0.32	0.43	0.21	0.27
`emo_Sexual_Lust`	-0.04	-0.13	0.02	-0.03
`emo_Shame`	-0.04	-0.11	0.04	0.04
`emo_Sourness`	0.06	0.14	0.12	0.29
`emo_Teasing`	0.09	0.16	0.03	0.06
`emo_Thankfulness_Gratitude`	-0.01	-0.07	-0.01	-0.07
`emo_Triumph`	0.03	0.07	0.03	0.07
`vn_AGEV_reg`	3.76	0.63	3.93	0.76
`vn_AROU_reg`	2.43	0.06	3.12	0.67
`vn_ARSH_reg`	2.83	0.29	2.67	0.10
`vn_ATCK_reg`	3.27	0.86	3.65	1.15
`vn_BKGN_reg`	3.52	1.07	3.62	1.20
`vn_BRGT_reg`	2.09	0.12	2.48	0.61
`vn_CHNK_reg`	0.68	-0.94	1.08	-0.62
`vn_CLRT_reg`	1.41	-0.64	1.52	-0.53
`vn_COGL_reg`	1.31	-0.74	0.90	-1.12
`vn_DARC_reg`	2.93	0.95	2.47	0.62
`vn_DFLU_reg`	0.61	-1.59	0.70	-1.51
`vn_EMPH_reg`	2.74	0.09	2.71	0.06
`vn_ESTH_reg`	1.87	-0.67	1.83	-0.74
`vn_EXPL_reg`	-0.03	-0.35	-0.05	-0.42
`vn_FOCS_reg`	1.87	-0.43	2.20	-0.13
`vn_FULL_reg`	3.12	1.51	3.66	2.11
`vn_GEND_reg`	5.22	0.74	5.27	0.77
`vn_HARM_reg`	1.51	-1.16	1.46	-1.22
`vn_METL_reg`	1.56	-0.06	1.65	0.03
`vn_RANG_reg`	1.60	-1.46	1.78	-1.26
`vn_RCQL_reg`	3.57	0.92	3.57	0.92
`vn_REGS_reg`	0.90	-0.24	1.24	0.03
`vn_RESP_reg`	4.28	1.51	4.89	2.09
`vn_ROUG_reg`	4.07	2.30	4.14	2.37
`vn_R_CHST_reg`	3.67	1.81	3.47	1.58
`vn_R_HEAD_reg`	0.21	-2.35	0.02	-2.59
`vn_R_MASK_reg`	0.70	-1.20	0.87	-1.04
`vn_R_MIXD_reg`	1.89	0.54	2.38	1.12
`vn_R_NASL_reg`	1.24	-1.48	1.12	-1.60
`vn_R_ORAL_reg`	2.16	-0.03	2.26	0.11
`vn_R_THRT_reg`	4.18	2.62	4.60	3.16
`vn_SMTH_reg`	1.94	-0.18	1.71	-0.39
`vn_STNC_reg`	1.99	-0.56	2.13	-0.44
`vn_STRU_reg`	1.01	-1.17	0.91	-1.28
`vn_S_ASMR_reg`	0.64	-0.52	1.05	-0.23
`vn_S_AUTH_reg`	1.11	0.02	0.99	-0.09
`vn_S_CART_reg`	0.28	-0.91	1.09	-0.33
`vn_S_CASU_reg`	1.97	-1.43	2.49	-1.02
`vn_S_CONV_reg`	0.78	-1.38	1.18	-1.07
`vn_S_DRAM_reg`	3.30	0.51	2.98	0.22
`vn_S_FORM_reg`	0.47	-0.71	0.19	-0.98
`vn_S_MONO_reg`	3.95	0.88	3.26	0.34
`vn_S_NARR_reg`	-0.12	-0.98	-0.25	-1.08
`vn_S_NEWS_reg`	0.17	-0.41	0.16	-0.44
`vn_S_PLAY_reg`	-0.25	-1.98	-0.07	-1.84
`vn_S_RANT_reg`	0.41	-0.62	0.14	-0.83
`vn_S_STRY_reg`	-0.39	-2.10	-0.23	-1.98
`vn_S_TECH_reg`	0.02	-0.51	0.00	-0.52
`vn_S_WHIS_reg`	1.25	-0.21	1.53	-0.04
`vn_TEMP_reg`	2.25	0.11	2.26	0.12
`vn_TENS_reg`	3.57	2.36	4.05	2.93
`vn_VALN_reg`	1.07	-1.12	1.26	-0.95
`vn_VALS_reg`	2.73	0.19	2.50	-0.02
`vn_VFLX_reg`	3.91	1.37	3.24	0.81
`vn_VOLT_reg`	1.87	-0.80	2.12	-0.53
`vn_VULN_reg`	3.53	0.89	3.72	1.09
`vn_WARM_reg`	2.76	0.20	2.71	0.15
`genuineness_0_6`	4.49	1.33	4.42	1.29
`blend_0_10`	7.73	0.38	7.83	0.42
`R_quality`	0.69	-1.20	0.71	-1.15
`eiv_extra:Age`	3.37	0.42	3.21	-0.15
`eiv_extra:Arousal`	1.53	0.56	1.63	0.79
`eiv_extra:Authenticity`	2.87	1.31	2.75	0.53
`eiv_extra:Background_Noise`	0.40	-1.53	0.51	-1.13
`eiv_extra:Confident_vs._Hesitant`	1.77	2.40	1.84	2.65
`eiv_extra:Gender`	-0.15	0.48	-0.70	-0.08
`eiv_extra:High-Pitched_vs._Low-Pitched`	1.21	-2.48	1.53	-1.20
`eiv_extra:Monotone_vs._Expressive`	0.93	-1.98	1.27	-1.26
`eiv_extra:Recording_Quality`	1.85	-0.90	1.73	-1.26
`eiv_extra:Serious_vs._Humorous`	-0.10	-3.02	0.11	-2.40
`eiv_extra:Soft_vs._Harsh`	0.48	0.61	0.33	0.17
`eiv_extra:Submissive_vs._Dominant`	-0.11	-1.50	0.03	-1.06
`eiv_extra:Valence`	-0.21	-0.57	-0.32	-0.85
`eiv_extra:Vulnerable_vs._Emotionally_Detached`	0.90	-1.86	0.98	-1.69
`eiv_extra:Warm_vs._Cold`	-0.42	-1.56	-0.18	-0.78
`eiv_extra:score_background_quality`	3.58	0.40	3.58	0.39
`eiv_extra:score_content_enjoyment`	3.96	-1.82	3.92	-1.94
`eiv_extra:score_overall_quality`	2.45	-0.40	2.33	-0.64
`eiv_extra:score_speech_quality`	1.88	0.49	1.88	0.53
`audiobox:CE`	4.52	-0.28	4.39	-0.40
`audiobox:CU`	6.74	1.09	6.72	1.07
`audiobox:PC`	1.21	-0.69	1.48	-0.53
`audiobox:PQ`	7.79	0.85	7.73	0.78
`dnsmos:SIG_raw`	3.05	-1.26	3.13	-1.15
`dnsmos:BAK_raw`	4.28	0.95	4.09	0.78
`dnsmos:OVRL_raw`	3.02	-0.08	2.98	-0.13
`dnsmos:SIG`	2.93	-1.12	2.95	-1.07
`dnsmos:BAK`	4.09	0.75	3.98	0.64
`dnsmos:OVRL`	2.75	-0.15	2.72	-0.19
`dnsmos:P808_MOS`	3.08	-0.69	3.03	-0.79
`burst_count_log1p`	1.27	1.97	1.15	1.77
`voiceclap_attribute:Affection`	-0.11	-1.91	-0.24	-2.14
`voiceclap_attribute:Age`	3.26	0.06	2.85	-0.69
`voiceclap_attribute:Amusement`	-0.31	-1.23	-0.10	-0.87
`voiceclap_attribute:Anger`	0.35	-1.27	0.15	-1.66
`voiceclap_attribute:Arousal`	0.94	-0.76	1.33	-0.14
`voiceclap_attribute:Astonishment_Surprise`	0.22	-0.60	0.39	-0.25
`voiceclap_attribute:Authenticity`	3.00	1.36	2.90	0.78
`voiceclap_attribute:Awe`	-0.09	-2.42	-0.15	-2.64
`voiceclap_attribute:Background_Noise`	0.29	-1.06	0.45	-0.45
`voiceclap_attribute:Bitterness`	0.19	-1.72	0.27	-1.36
`voiceclap_attribute:Concentration`	0.25	-1.81	0.31	-1.70
`voiceclap_attribute:Confident_vs._Hesitant`	1.29	0.48	1.33	0.57
`voiceclap_attribute:Confusion`	0.16	-1.45	0.05	-1.78
`voiceclap_attribute:Contemplation`	0.59	-0.47	0.51	-0.67
`voiceclap_attribute:Contempt`	0.11	-1.75	0.04	-1.99
`voiceclap_attribute:Contentment`	0.14	-1.45	0.08	-1.67
`voiceclap_attribute:Disappointment`	0.50	-0.88	0.69	-0.23
`voiceclap_attribute:Disgust`	0.15	-2.31	0.12	-2.42
`voiceclap_attribute:Distress`	1.51	1.67	1.61	1.95
`voiceclap_attribute:Doubt`	0.58	0.23	0.37	-0.87
`voiceclap_attribute:Elation`	-0.10	-1.61	0.07	-1.17
`voiceclap_attribute:Embarrassment`	0.07	-0.75	0.09	-0.70
`voiceclap_attribute:Emotional_Numbness`	0.24	-1.60	0.26	-1.51
`voiceclap_attribute:Fatigue_Exhaustion`	1.79	5.07	2.19	6.63
`voiceclap_attribute:Fear`	0.31	-1.45	0.37	-1.15
`voiceclap_attribute:Gender`	0.01	0.16	-0.26	-0.11
`voiceclap_attribute:Helplessness`	1.39	2.71	1.32	2.46
`voiceclap_attribute:High-Pitched_vs._Low-Pitched`	1.03	-2.15	1.11	-1.95
`voiceclap_attribute:Hope_Enthusiasm_Optimism`	-0.28	-2.48	-0.10	-2.02
`voiceclap_attribute:Impatience_and_Irritability`	0.52	-0.98	0.44	-1.13
`voiceclap_attribute:Infatuation`	-0.06	-2.02	-0.06	-2.02
`voiceclap_attribute:Interest`	-0.27	-4.24	-0.38	-4.49
`voiceclap_attribute:Intoxication_Altered_States_of_Consciousness`	0.13	-0.81	0.10	-0.88
`voiceclap_attribute:Jealousy_&_Envy`	0.00	-2.13	0.05	-1.91
`voiceclap_attribute:Longing`	0.12	-1.89	0.07	-2.15
`voiceclap_attribute:Malevolence_Malice`	0.13	-2.04	0.05	-2.26
`voiceclap_attribute:Monotone_vs._Expressive`	0.95	-1.39	0.96	-1.38
`voiceclap_attribute:Pain`	0.81	1.95	0.79	1.87
`voiceclap_attribute:Pleasure_Ecstasy`	-0.09	-1.96	0.03	-1.58
`voiceclap_attribute:Pride`	-0.15	-2.67	0.12	-1.89
`voiceclap_attribute:Recording_Quality`	2.14	-0.52	1.99	-1.00
`voiceclap_attribute:Relief`	0.28	-1.80	0.54	-1.18
`voiceclap_attribute:Sadness`	0.67	-0.27	0.63	-0.38
`voiceclap_attribute:Serious_vs._Humorous`	0.57	-0.41	0.54	-0.47
`voiceclap_attribute:Sexual_Lust`	0.00	-1.51	-0.01	-1.54
`voiceclap_attribute:Shame`	0.10	-1.52	0.07	-1.63
`voiceclap_attribute:Soft_vs._Harsh`	0.52	1.01	0.45	0.81
`voiceclap_attribute:Sourness`	0.28	-1.47	0.24	-1.60
`voiceclap_attribute:Submissive_vs._Dominant`	0.18	-1.23	0.26	-1.01
`voiceclap_attribute:Teasing`	-0.26	-2.12	-0.17	-1.87
`voiceclap_attribute:Thankfulness_Gratitude`	-0.01	-2.64	0.12	-2.39
`voiceclap_attribute:Triumph`	-0.24	-2.66	-0.03	-2.08
`voiceclap_attribute:Valence`	-0.67	-1.05	-0.50	-0.77
`voiceclap_attribute:Vulnerable_vs._Emotionally_Detached`	0.58	-1.90	0.58	-1.90
`voiceclap_attribute:Warm_vs._Cold`	0.09	0.39	-0.32	-0.62
`voiceclap_attribute:duration`	3.42	-1.18	3.22	-1.21
`voiceclap_attribute:score_background_quality`	3.27	0.05	3.38	0.28
`voiceclap_attribute:score_content_enjoyment`	4.50	-1.08	4.47	-1.25
`voiceclap_attribute:score_overall_quality`	2.37	-0.64	2.34	-0.73
`voiceclap_attribute:score_speech_quality`	2.00	1.51	1.99	1.39
`voiceclap_attribute:talking_speed`	3.38	-1.50	2.56	-1.72

← All 50 examples ← Previous Next →